Home /
Research
Showing 733 - 738 / 904
Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles
ChristopherClark, MarkYatskar, LukeZettlemoyer....
Published date-11/07/2020
NaturalLanguageInference, QuestionAnswering, VisualQuestionAnswering
Many datasets have been shown to contain incidental correlations created by idiosyncrasies in the data collection process. For example, sentence entailment datasets can have spurious word-class correlations if nearly all …
TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation
YujiaZhang, QianzhongLi, XiaoguangZhao....
Published date-11/07/2020
Regular pavement inspection plays a significant role in road maintenance for safety assurance. Existing methods mainly address the tasks of crack detection and segmentation that are only tailored for long-thin …
Depthwise Multiception Convolution for Reducing Network Parameters without Sacrificing Accuracy
GuoqingBao, ManuelB.Graeber, XiuyingWang....
Published date-11/07/2020
Deep convolutional neural networks have been proven successful in multiple benchmark challenges in recent years. However, the performance improvements are heavily reliant on increasingly complex network architecture and a high …
Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation
HaryoAkbariantoWibowo, TatagAzizPrawiro, MuhammadIhsan....
Published date-11/06/2020
MachineTranslation, StyleTransfer
In its daily use, the Indonesian language is riddled with informality, that is, deviations from the standard in terms of vocabulary, spelling, and word order. On the other hand, current …
Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss
DongseokShim, H.JinKim....
Published date-11/06/2020
DepthEstimation, MonocularDepthEstimation, ObjectDetection, Self-SupervisedLearning
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based …
An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish
QuanDuong, MikaHämäläinen, SimonHengchen....
Published date-11/06/2020
MachineTranslation, OpticalCharacterRecognition
Historical corpora are known to contain errors introduced by OCR (optical character recognition) methods used in the digitization process, often said to be degrading the performance of NLP systems. Correcting …